Gene expression and splicing alterations analyzed by high throughput RNA sequencing of chronic lymphocytic leukemia specimens

Abstract

Background: To determine differentially expressed and spliced RNA transcripts in chronic lymphocytic leukemia specimens a high throughput RNA-sequencing (HTS RNA-seq) analysis was performed.

Methods: Ten CLL specimens and five normal peripheral blood CD19+ B cells were analyzed by HTS RNA-seq. The library preparation was performed with Illumina TrueSeq RNA kit and analyzed by Illumina HiSeq 2000 sequencing system.

Results: An average of 48.5 million reads for B cells, and 50.6 million reads for CLL specimens were obtained with 10396 and 10448 assembled transcripts for normal B cells and primary CLL specimens respectively. With the Cuffdiff analysis, 2091 differentially expressed genes (DEG) between B cells and CLL specimens based on FPKM (fragments per kilobase of transcript per million reads and false discovery rate, FDR q < 0.05, fold change >2) were identified. Expression of selected DEGs (n = 32) with up regulated and down regulated expression in CLL from RNA-seq data were also analyzed by qRT-PCR in a test cohort of CLL specimens. Even though there was a variation in fold expression of DEG genes between RNA-seq and qRT-PCR; more than 90 % of analyzed genes were validated by qRT-PCR analysis. Analysis of RNA-seq data for splicing alterations in CLL and B cells was performed by Multivariate Analysis of Transcript Splicing (MATS analysis). Skipped exon was the most frequent splicing alteration in CLL specimens with 128 significant events (P-value <0.05, minimum inclusion level difference >0.1).

Conclusion: The RNA-seq analysis of CLL specimens identifies novel DEG and alternatively spliced genes that are potential prognostic markers and therapeutic targets. High level of validation by qRT-PCR for a number of DEG genes supports the accuracy of this analysis. Global comparison of transcriptomes of B cells, IGVH non-mutated CLL (U-CLL) and mutated CLL specimens (M-CLL) with multidimensional scaling analysis was able to segregate CLL and B cell transcriptomes but the M-CLL and U-CLL transcriptomes were indistinguishable. The analysis of HTS RNA-seq data to identify alternative splicing events and other genetic abnormalities specific to CLL is an added advantage of RNA-seq that is not feasible with other genome wide analysis.

Fig. 1

Distribution of sequencing reads in normal B cells and CLL specimens. a The bar diagram represents distribution of uniquely mapped reads to human genome UCSC_hg19 (GRCh37). Each bar depicts the percentage of reads from individual samples (five normal B cell and ten CLL specimens) mapped to coding sequence exon (CDS_exon), 5’ and 3’ untranslated regions (5’ and 3’UTR_Exons), introns and intergenic regions. b Pie charts represent the average percentage of sequencing reads from five normal B cell (left) and ten CLL specimens (right) that map to the above mentioned regions

Fig. 2

Transcriptomic expression profiles and validation. a The number of statistically significant differentially (Up and Down regulated) expressed genes identified from Cuffdiff analysis in various groups relative to B cells are shown in a table format. The differentially expressed genes (DEG, FDR-adjusted q-value < 0.05, Fold change > 2) in all CLL specimens (n = 10), U-CLL (n = 6) and M-CLL (n = 4) was compared to normal B cells. b Venn diagram illustrates the overlapped DEG between the three groups in panel A

Fig. 3

Validation analysis of selected differentially expressed genes. a qRT-PCR of selected genes on B cells (n = 5), CLL specimens, RNA seq cohort (n = 5) and CLL specimens, test cohort (n = 47). Data shown is the delta delta cT relative to actin. (Mean and standard deviation). Table below panel A shows the P-values of the qRT-PCR data for the comparison of B cells and CLL RNA seq cohort (n = 10), and B cells and CLL test cohort. (t-test). b Fold expression of selected genes in the larger CLL cohort (n = 47) based on qRT-PCR analysis. * PTPRK expression was not detected in normal B cells therefore fold change could not be calculated

Fig. 4

Transcriptomic comparison of IgVH mutated (M-CLL) and non-mutated (U-CLL). a Table with Cuffdiff data showing significant differentially expressed genes between M- and U-CLL specimens. b MDS plot (Multi-Dimensional Scaling) shows the clustering of the transcriptomic expression profiles of normal B cells (B1-B5), U-CLL and M-CLL samples (numbered as in Table 1). Axes in the MDS plot (M1 and M2) are arbitrary, and the values on the axes are distance units. c, d, e qRT-PCR data from the RNA-seq cohort of CLL specimens (n = 10) for three selected genes (T, IGLL5 and TFEC) (relative to actin, log scale). These panels show the scatter-plot qRT-PCR data in a separate cohort of CLL specimens and compare the expression of the three selected genes in M and U-CLL specimens. The dotted line separates the M- and U-CLL specimens

Fig. 5

Alternative splicing events in B and CLL specimens. a Schematic showing alternative splicing (AS) events (from MATS analysis website). b Table with MATS analysis data with different AS events, total events and significant events are shown. B and CLL columns indicate the events out of all the significant events that had higher inclusion levels in either B or CLL specimens

Fig. 6

Validation of alternative splicing events. RT-PCR analysis of six AS events. For each gene, five B cell specimens and nine CLL specimen was analyzed. Expected bp (base pair) of the DNA fragments, with schematic of the skipped exon and mean Inc level (inclusion level, based on gel densitometry) are shown